Thu, Jun 28 PM
13:00 - 17:30 |
| (1) |
13:00-13:30 |
On Diamond Covering in Similar Segment Search RDDS Algorithm |
Masahide Sugiyama (UoA) |
| (2) |
13:30-14:00 |
An Efficient Algorithm for Similar Segment Search
-- Implementation and Evaluation in Three Time-Series -- |
Akihiro Sakai, Masahide Sugiyama (UoA) |
| (3) |
14:00-14:30 |
An integration method of plural subword models for spoken document retrieval
-- Utilization of retrieval performance expectation of a query among subword model -- |
Yoshiaki Itoh, Kohei Iwata, Kazunori Kojima, Masaaki Ishigame (Iwate Pref. Univ), Kazuyo Tanaka (Univ. of Tsukuba), Shi-wook Lee (AIST) |
| |
14:30-14:45 |
Break ( 15 min. ) |
| (4) |
14:45-15:15 |
Speech and song wave search in the Web : System Design and Implementation |
Yuichi Yaguchi, Yoshiyuki Watanabe, Keitaro Naruse, Ryuichi Oka (Univ. of Aizu) |
| (5) |
15:15-15:45 |
Detection of acoustic event boundaries from continuous speech based on constrained clustering |
Naoya Shimomura, Satoshi Asakawa, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) |
| (6) |
15:45-16:15 |
Optimization of Question Answer Database Based on Leave-one-out Cross Validation |
Shota Takeuchi, Tobias Cincarek, Manabu Kida, Naoki Hayakawa, Hiromichi Kawanami, Hiroshi Saruwatari, Kiyohiro Shikano (NAIST) |
| |
16:15-16:30 |
Break ( 15 min. ) |
| (7) |
16:30-17:00 |
Speech Reproduction with Optimum Speed Using Flexible Time-Scale Framework |
Kota Takahashi (UEC) |
| (8) |
17:00-17:30 |
Influence of Echoes to Primary Sound Integration and Segregation Factors in Human Audition |
Yuya Futamura, Hitomi Sato, Jie Huang (Univ. of Aizu) |
Fri, Jun 29 AM
09:30 - 15:20 |
| (1) |
09:30-10:00 |
Noise Suppression Based on Search with Multi-Noise Composite Models |
Takatoshi Jitsuhiro, Tomoji Toriyama, Kiyoshi Kogure (ATR) |
| (2) |
10:00-10:30 |
Voice Activity Detection Applied to Hands-Free Speech Recognition based on Decoding using Acoustic and Language Models |
Hiroyuki Sakai, Tobias Cincarek, Hiromichi Kawanami, Hiroshi Saruwatari, Kiyohiro Shikano (NAIST), Akinobu Lee (Nagoya Inst. of Tech.) |
| |
10:30-10:50 |
Break ( 20 min. ) |
| (3) |
10:50-11:20 |
An investigation on speaker vector-based speaker identification under noisy conditions |
Yuki Goto, Tatsuya Akatsu, Masaharu Katoh, Tetsuo Kosaka, Masaki Kohda (Yamagata Univ.) |
| (4) |
11:20-11:50 |
Automatic detection and estimation of the direction of calling speech under noisy envirionment |
Motoyuki Suzuki, Kouta Kitadate, Akinori Ito, Shozo Makino (Tohoku Univ.) |
| |
11:50-13:00 |
Break ( 70 min. ) |
| (5) |
13:00-13:30 |
Improvement of unsupervised adaptation in lecture speech recognition |
Takashi Kusama, Yohei Okuyama, Masaharu Katoh, Tetsuo Kosaka, Masaki Kohda (Yamagata Univ.) |
| (6) |
13:30-14:00 |
Hierarchical Spoken Word Recognition System Using Probabilistic Distances from a Group of Templates with Long-Time Structures |
Ken-ichi Kato, Tetsuji Ogawa, Tetsunori Kobayashi (Waseda Univ.) |
| |
14:00-14:20 |
Break ( 20 min. ) |
| (7) |
14:20-14:50 |
Automatic Speech Recognition using Narrow-band Analytic Signal and Non-linear Discriminant Analysis |
Yotaro Kubo (Waseda Univ.), Shigeki Okawa (CIT), Akira Kurematsu, Katsuhiko Shirai (Waseda Univ.) |
| (8) |
14:50-15:20 |
The Time-Reversal Acoustics in Ergodic Cavity: Some Simulation and Experiment Results |
Shuxue Ding, Satoshi Matsuoka, Naoto Sakurai (Univ. of Aizu) |